Model comparison
Claude 3.5 Sonnet vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 34.6 on the Noometry Index.
Last verified . 40 shared benchmarks.
Summary
- They share 40 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 4 categories and o3-mini in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3-mini leads 38.3 to 28.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 76.9% for o3-mini.
Side by side
| Claude 3.5 Sonnet | o3-mini | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 34.6 | 36.7 |
| Released | 2024-06-20 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 60 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Claude 3.5 Sonnet: 39.0 (#165), o3-mini: 40.8 (#132)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| Aider Polyglot | 51.6% | 60.4% |
| GSO | 4.6% | 1.3% |
| WeirdML | 40% | 43.7% |
| LiveBench Coding | 67.1% | 82.7% |
| LMArena Coding | 1342 | 1378 |
| CadEval | 48% | 54% |
| SciCode | — | 39.8% |
| BigCodeBench Instruct | 46.8% | — |
| BigCodeBench Complete | 58.6% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), o3-mini: 29.6 (#84)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| Cybench | 17.5% | 22.5% |
| TheAgentCompany | 24% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), o3-mini: 16.3 (#305)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| SimpleBench | 41.4% | 22.8% |
| LiveBench Reasoning | 56.7% | 89.6% |
| LMArena Hard Prompts | 1305 | 1366 |
| DTBench | 67.8% | 68.8% |
| LiveBench Data Analysis | 55% | 70.6% |
| Epoch Capabilities Index | 133.55 | 140.34 |
| ForecastBench | 60.7 | 59.6 |
| LiveBench | 59% | 75.9% |
| ARC-AGI-2 | — | 3% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| EnigmaEval | 0.9% | — |
| Mystery Game Puzzles | — | 7% |
| LMCA | — | 19% |
Math o3-mini leads
Claude 3.5 Sonnet: 19.2 (#288), o3-mini: 28.1 (#244)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 76.9% |
| LiveBench Math | 52.3% | 77.3% |
| LMArena Math | 1307 | 1396 |
| MATH Level 5 | 56.9% | 96.5% |
| FrontierMath (Feb 2025 set) | 2.1% | 12.4% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| Omni-MATH | 27.6% | — |
Knowledge o3-mini leads
Claude 3.5 Sonnet: 28.6 (#245), o3-mini: 38.3 (#146)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| GPQA Diamond | 55.3% | 77% |
| Confabulations | 19.9% | 17.9% |
| LMArena Expert | 1265 | 1364 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.5 (#120), o3-mini: —
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual o3-mini leads
Claude 3.5 Sonnet: 43.2 (#185), o3-mini: 45.7 (#164)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| LMArena Non-English | 1283 | 1319 |
| LMArena Chinese | 1272 | 1379 |
| LMArena French | 1305 | 1334 |
| LMArena German | 1297 | 1303 |
| LMArena Japanese | 1234 | 1286 |
| LMArena Korean | 1200 | 1314 |
| LMArena Russian | 1306 | 1304 |
| LMArena Spanish | 1290 | 1321 |
Instruction Following o3-mini leads
Claude 3.5 Sonnet: 68.8 (#182), o3-mini: 75.1 (#72)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 69.3% | 84.4% |
| LMArena Instruction Following | 1297 | 1337 |
| IFEval | 85.5% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#167), o3-mini: 33.8 (#256)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| LMArena Longer Query | 1311 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 52.9 (#164), o3-mini: 50.3 (#182)
| Benchmark | Claude 3.5 Sonnet | o3-mini |
|---|---|---|
| LMArena Text | 1298 | 1337 |
| LMArena Creative Writing | 1292 | 1286 |
| Short-Story Creative Writing | 80.3% | 61.7% |
| LMArena Multi-Turn | 1326 | 1320 |
| LiveBench Language | 53.8% | 50.7% |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and o3-mini share?
40 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and o3-mini has 51.